Live / DigitalOcean / Incident
DigitalOcean: Serverless Inference - Gemma4 Latency Issues Causing Timeouts & Slow Responses
DigitalOcean · digitalocean.comMinor incidentResolved2026-07-15 21:46 UTC
Public — what happened
Summary
DigitalOcean said that starting on July 13, 2026 at 19:04 UTC, customers using the Gemma 4 model on its Serverless Inference and Dedicated Inference platforms could see very slow responses or requests that timed out. The company attributed the problem to a backend configuration issue and reported deploying a fix that evening at 22:24 UTC, but the slowdowns returned on July 14 at 11:07 UTC, this time described as affecting Serverless Inference. DigitalOcean said a second fix went out on July 15 at 10:06 UTC, and it marked the incident resolved at 21:46 UTC that day, saying Gemma 4 response times were back to normal.
Affected
Inference
Timeline
- Started — 2026-07-13 19:04 UTC
- Identified — 2026-07-13 19:04 UTC
- Monitoring — 2026-07-13 22:24 UTC
- Identified — 2026-07-14 11:07 UTC
- Monitoring — 2026-07-15 10:06 UTC
- Resolved — 2026-07-15 21:46 UTC · 2 days after it started
With SquidGrid — where it starts on the route
Independent path health
The status page is the symptom. SquidGrid measures the paths that reach DigitalOcean against their own baselines — whether the routes carrying your traffic degraded, at which handoff, and who owns that stretch.
🔒 Sign in to seeCustomers get the live Provider Assessment Report for DigitalOcean: paths off baseline right now, where on the route conditions change, and its full incident track record.
Included with any paid plan.
Open the DigitalOcean report →
More from DigitalOcean